[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120521-en":3,"doc-seo-120521-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120521,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Machine Learning-based Search of High-redshift Quasars - Draft","A machine learning framework is developed to search for high-redshift quasars with 5.0 \u003C z \u003C 6.5 by combining photometric data from the DESI Imaging Legacy Surveys and the WISE survey. The study analyzes missing-value imputation, feature selection, and comparisons among multiple algorithms, then evaluates ensemble choices for the training sample. A 11-class random forest model is found highly effective, reaching 96.43% precision, 91.53% recall, and up to 82.20% completeness. The resulting catalog lists 216,949 high-redshift quasar candidates with 476 high-probability systems, publicly released, and validation using MUSE and DESI-EDR spectra confirms 14 and 20 true high-redshift quasars from 21 candidates.","arXiv :2409 .02167v1 [ astro-ph .GA] 3 Sep 2024  \nDraft version September 5, 2024  \nTypeset using LATEX twocolumn style in AASTeX631  \nMachine Learning-based Search of High-redshift Quasars  \nGuangping Ye (叶广平) ,1 Huanian Zhang (张华年) ,1, 2 and Qingwen Wu (吴庆文) 1  \n1 Department of Astronomy, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China  \n2 Steward Observatory, University of Arizona, Tucson, AZ 85719, USA  \nABSTRACT  \nWe present a machine learning search for high-redshift (5 .0 \u003C z \u003C 6.5) quasars using the combined photometric data from the DESI Imaging Legacy Surveys and the WISE survey. We explore the imputation of missing values for high-redshift quasars, discuss the feature selections, compare different machine learning algorithms, and investigate the selections of class ensemble for the training sample, then we find that the random forest model is very effective in separating the high-redshift quasars from various contaminators. The 11-class random forest model can achieve a precision of 96 .43% and arecall of 91 .53% for high-redshift quasars for the test set. We demonstrate that the completeness of the high-redshift quasars can reach as high as 82 .20% . The final catalog consists of 216,949 high-redshift quasar candidates with 476 high probable ones in the entire Legacy Surveys DR9 footprint, and we make the catalog publicly available. Using MUSE and DESI-EDR public spectra, we find that 14 true high-redshift quasars (11 in the training sample) out of 21 candidates are correctly identified for MUSE, and 20 true high-redshift quasars (11 in the training sample) out of 21 candidates are correctly identified for DESI-EDR. Additionally, we estimate photometric redshift for the high-redshift quasar candidates using random forest regression model with a high precision.  \nKeywords: cosmology: observations – quasars: high-redshift – quasars: search  \n1. INTRODUCTION  \nQuasars in general are driven by a supermassive black hole (SMBH) at the centre of the host galaxy through a process of accretion, and are the brightest non-transient sources of light in the Universe. SMBH activities are a key ingredient of galaxy formation, and are critical to subsequent galaxy evolution. Quasars at z > 5 are often referred to as high-redshift quasars since they are at the end of the reionization epoch of the Universe, when the vast majority of the Universe’s neutral hydrogen has been reionised (Eilers et al. 2018; Yang et al. 2020; Bosman et al. 2022) . High-redshift quasars provide effective probes for the study of galaxy evolution and cosmology, including the evolution of the intergalactic medium (IGM, Pentericci et al. 2002; Fan et al. 2006b; Becker et al. 2007; Bosman et al. 2018; Eilerset al. 2018; Yang et al. 2020) and the circumgalactic  \n[guangping@hust.edu.cn](guangping@hust.edu.cn)  \n[huanian@hust.edu.cn](huanian@hust.edu.cn)  \nmedium (CGM, Zou et al. 2021; Davies et al. 2023a,b; Zou et al. 2024), the formation of early supermassive black holes, the co-evolution of SMBH and their host galaxies (Volonteri 2012) .  \nThere exist many challenges in searching and verifying high-redshift quasars. On one hand, the number density of high-redshift quasars is very low in the Universe (Zhang et al. 2023 , 2024), resulting to a small number of observable high-redshift quasars, which means that the single-object spectroscopic observations on largeaperture telescope of quasar candidates are needed and expensive; on the other hand, the contamination is overwhelming and could be a few orders of magnitude more than signals (Barnett et al. 2019) . The major contaminations include cool galactic dwarfs with spectral types of M, L, and T (Fan et al. 2023), which are similar to those of high-redshift quasars in the color space constructed from optical and near-infrared broad-band photometry.  \nThe traditional method for searching the high-redshift quasars is the color-cut selection (Warren et al. 1987) based on color drop-out, wh","cbCaifYZTz0sexnz","https://ap.wps.com/l/cbCaifYZTz0sexnz","pdf",2931959,1,26,"English","en",105,"# Abstract\n# Introduction\n## Quasars and high-redshift targets\n## Challenges and contamination\n## Traditional color-cut selection\n## Motivation for machine learning","[{\"question\":\"What data sets are combined for the machine learning search of high-redshift quasars?\",\"answer\":\"The method uses combined photometric data from the DESI Imaging Legacy Surveys and the WISE survey.\"},{\"question\":\"Which machine learning model performs best for separating high-redshift quasars from contaminators?\",\"answer\":\"An 11-class random forest model is reported as very effective for separating high-redshift quasars from contaminants.\"},{\"question\":\"How are the candidate quasars validated, and what success rates are reported?\",\"answer\":\"Using MUSE and DESI-EDR public spectra, 14 true high-redshift quasars are correctly identified for MUSE out of 21 candidates, and 20 are correctly identified for DESI-EDR out of 21 candidates.\"}]","Machine Learning-based Search of High-redshift Quasars - Draft | PDF",1785730476,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-based-search-of-high-redshift-quasars-draft","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-based-search-of-high-redshift-quasars-draft/120521/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data sets are combined for the machine learning search of high-redshift quasars?","Question",{"text":75,"@type":76},"The method uses combined photometric data from the DESI Imaging Legacy Surveys and the WISE survey.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning model performs best for separating high-redshift quasars from contaminators?",{"text":80,"@type":76},"An 11-class random forest model is reported as very effective for separating high-redshift quasars from contaminants.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the candidate quasars validated, and what success rates are reported?",{"text":84,"@type":76},"Using MUSE and DESI-EDR public spectra, 14 true high-redshift quasars are correctly identified for MUSE out of 21 candidates, and 20 are correctly identified for DESI-EDR out of 21 candidates.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]